"Negative dimension size caused by subtracting 36 from 11" Error from Conv2D layer in Keras model

I am trying to create a handwriting recognition model based on this graph I found. However I am faced with this error. Here is my code:

  model.add(keras.Input(shape=(32, 32, 3)))
  model.add(layers.Conv2D(32, 3, padding="valid", activation="relu"))
  model.add(layers.Conv2D(30, 20, activation="relu"))
  model.add(layers.Conv2D(28, 36, activation="relu"))
  model.add(layers.MaxPooling2D(pool_size=(26, 26)))
  model.add(layers.Conv2D(13, 52, activation="relu"))
  model.add(layers.Conv2D(11, 68, activation="relu"))
  model.add(layers.Conv2D(9, 84, activation="relu"))
  model.add(layers.MaxPooling2D(pool_size=(6, 6)))
  model.add(layers.Conv2D(3, 100, activation="relu"))
  model.add(layers.Dropout(116, input_shape=(1, 1)))
  model.add(tf.keras.layers.Dense(116, activation='relu'))
  sgd = optimizers.SGD(learning_rate=0.001, momentum=0.9, nesterov=True)
  model.compile(loss=tf.keras.losses.BinaryCrossentropy(), optimizer=sgd, metrics=['accuracy'])
  accuracy_score = model.score(X_train, Y_train)
How many English words
do you know?
Test your English vocabulary size, and measure
how many words do you know
Online Test
Powered by Examplum